论文标题
基于链条的判别自动编码器用于语音识别
Chain-based Discriminative Autoencoders for Speech Recognition
论文作者
论文摘要
在我们以前的工作中，我们提出了一个歧视性自动编码器（DCAE）进行语音识别。 DCAE将两个训练方案结合在一起。首先，由于DCAE的目标是学习编码器映射，因此重建语音和输入语音之间的平方错误被最小化。其次，在代码层中，基于框架的语音嵌入是通过最大程度地减少地面真相标签和预测的Triphone-State评分之间的分类跨熵来获得的。 DCAE是根据Kaldi工具包开发的，通过将各种TDNN模型视为编码器。在本文中，我们进一步提出了三个新版本的DCAE。首先，使用了一个新的目标函数，该函数使用了地面真相和预测的Triphone-State序列之间的分类跨膜和相互信息。所得的DCAE称为基于链的DCAE（C-DCAE）。为了应用于强大的语音识别，我们将C-DCAE进一步扩展到层次和平行结构，从而导致HC-DCAE和PC-DCAE。在这两个模型中，重建的嘈杂语音与输入嘈杂的语音以及增强语音和参考清洁语音之间的误差之间的误差都归功于目标函数。 WSJ和Aurora-4 Corpora的实验结果表明，我们的DCAE模型优于基线系统。
In our previous work, we proposed a discriminative autoencoder (DcAE) for speech recognition. DcAE combines two training schemes into one. First, since DcAE aims to learn encoder-decoder mappings, the squared error between the reconstructed speech and the input speech is minimized. Second, in the code layer, frame-based phonetic embeddings are obtained by minimizing the categorical cross-entropy between ground truth labels and predicted triphone-state scores. DcAE is developed based on the Kaldi toolkit by treating various TDNN models as encoders. In this paper, we further propose three new versions of DcAE. First, a new objective function that considers both categorical cross-entropy and mutual information between ground truth and predicted triphone-state sequences is used. The resulting DcAE is called a chain-based DcAE (c-DcAE). For application to robust speech recognition, we further extend c-DcAE to hierarchical and parallel structures, resulting in hc-DcAE and pc-DcAE. In these two models, both the error between the reconstructed noisy speech and the input noisy speech and the error between the enhanced speech and the reference clean speech are taken into the objective function. Experimental results on the WSJ and Aurora-4 corpora show that our DcAE models outperform baseline systems.
